Code, Data & Artifacts for Multi-Fault Diagnosis Using Lightweight Machine Learning Techniques for Rotordynamics Analysis in Multi-Domain

OverviewThis record provides the reproducibility package (code and supporting artifacts) for the manuscript:“Multi-Fault Diagnosis Using Lightweight Machine Learning Techniques for Rotordynamics Analysis in Multi-Domain”. Dataset COMFAULDA (IEEE DataPort) — DOI: 10.21227/89ye-ap56 Note: this record does not redistribute the COMFAULDA dataset; it must be downloaded from IEEE DataPort using the DOI above. ROSS signal generated available at ROSS_signals_generated.zip file. What this record contains Source code for preprocessing, feature extraction, training, and evaluation Configuration files used in the experiments Trained model artifacts (as used in the paper) Extracted feature tables and the source data used to generate all figures Deployed system code (edge/on-prem components) How to reproduce the results Download COMFAULDA from IEEE DataPort using DOI: 10.21227/89ye-ap56 Download this package and follow the instructions in the README Run the provided scripts to regenerate features, metrics, and figure/table outputs Code repository (development version)https://github.com/AmandaRosa/paper-code-artifact/ Recommended citationPlease cite this Zenodo record (DOI shown by Zenodo after publication) and the associated manuscript.